Added Morgan fingerprint example [skip ci]

Author: ankane

README.md

@@ -25,6 +25,7 @@ Or check out some examples:
 
 - [Embeddings](examples/openai_embeddings.rb) with OpenAI
 - [Binary embeddings](examples/cohere_embeddings.rb) with Cohere
+- [Morgan fingerprints](examples/morgan_fingerprints.rb) with RDKit.rb
 - [Topic modeling](examples/topic_modeling.rb) with tomoto.rb
 - [User-based recommendations](examples/disco_user_recs.rb) with Disco
 - [Item-based recommendations](examples/disco_item_recs.rb) with Disco

examples/Gemfile

@@ -5,5 +5,6 @@ gemspec path: ".."
 gem "disco"
 gem "numo-narray"
 gem "pg"
+gem "rdkit-rb"
 gem "sequel"
 gem "tomoto"

examples/morgan_fingerprints.rb

@@ -0,0 +1,25 @@
+require "pg"
+require "rdkit-rb"
+
+def generate_fingerprint(molecule)
+  RDKit::Molecule.from_smiles(molecule).morgan_fingerprint
+end
+
+conn = PG.connect(dbname: "pgvector_example")
+conn.exec("CREATE EXTENSION IF NOT EXISTS vector")
+
+conn.exec("DROP TABLE IF EXISTS molecules")
+conn.exec("CREATE TABLE molecules (id text PRIMARY KEY, fingerprint bit(2048))")
+
+molecules = ["Cc1ccccc1", "Cc1ncccc1", "c1ccccn1"]
+molecules.each do |molecule|
+  fingerprint = generate_fingerprint(molecule)
+  conn.exec_params("INSERT INTO molecules (id, fingerprint) VALUES ($1, $2)", [molecule, fingerprint])
+end
+
+query_molecule = "c1ccco1"
+query_fingerprint = generate_fingerprint(query_molecule)
+result = conn.exec_params("SELECT id, fingerprint <%> $1 AS distance FROM molecules ORDER BY distance LIMIT 5", [query_fingerprint])
+result.each do |row|
+  p row
+end